pull down to refresh

A couple months ago I launched Bookmarked as a library of book recommendations from interesting people.
Each book recommendation requires collecting a lot of data from different sources. Books all have images, genres, synopses, and people recommending books may share their recommendation on Twitter, on YouTube, on podcasts, or even in the foreword of the book itself.
To streamline this data collection process I’ve been working with Stakwork to build an automated workflow that can collect new book recommendations from interesting people faster than a human can.
This week we did our first test run, and I’m optimistic that it will continue to generate 10-100x cost savings at scale.
This week's workflow cost 1,358 sats (paid over Lightning) and saved me 30 minutes of data collection.
There are a number of steps in the workflow. Some rely on APIs to fetch and filter data, while other parts of the workflow send mini-tasks to be solved by human workers (ex. to determine whether someone’s mention of a book is an actual recommendation or simply a mention).
Pretty cool way to use Bitcoin to cut down on data collection costs and help me scale up the Bookmarked library.
1255 sats \ 0 replies \ @0fje0 6 Jan
Very interesting. First time seeing Stakwork.
Looks like something to look into.
reply
982 sats \ 1 reply \ @davidw 6 Jan
Great to see the savings and product. Proving time = money.
  1. So this is looking to supplant GoodReads?
  2. Would be cool if people could create their own summaries (enabled by AI) and discuss key topics like @elvismercury does here. Could get people reading way more.
reply
475 sats \ 0 replies \ @kr OP 6 Jan
Thanks! I really just wanted to have a library of recommendations that I could pull from, and figured others might want the same… I’m not sure the site will be much more than a directory.
All of the synopses on each book page are actually generated by AI today, but agree that it would be cool to see more book discussions on here.
reply
Great idea, love the use case.
A site I love is Five books that has some overlap with your idea. I love reading through how experts view other experts. Maybe some ideas to steal there.
reply
I don't love how I used love three times in four sentences, though.
reply
very cool!
reply
Very cool, like the way it auto searches as you type
reply
This is an awesome use case. I love the creative thinking and foresight! This is what we need more of. Keep up the good work!
reply
604 sats \ 1 reply \ @TNStacker 6 Jan
Great Proof of Work, sir!
reply
10 sats \ 0 replies \ @kr OP 6 Jan
🫡
reply
601 sats \ 1 reply \ @grayruby 6 Jan
Pretty impressive for a Leafs fan.
reply
50 sats \ 0 replies \ @kr OP 6 Jan
😂
reply
601 sats \ 0 replies \ @AJ1992 6 Jan
Bad ass
reply
A couple months ago I launched Bookmarked as a library of book recommendations from interesting people. Each book recommendation requires collecting a lot of data from different sources.
some people on the lists there are indeed interesting, but there are already tons of sites doing the same, what would make your site stand out?
personally, I would prefer getting book recommendations from stackers whom I find interesting in certain topics, and I can even interact with them to discuss - don't we have book recommendations here too? possible to integrate? I feel that would potentially really make your site stand out instead of just collecting a lot of data from different sources like everybody.
To streamline this data collection process I’ve been working with Stakwork to build an automated workflow that can collect new book recommendations from interesting people faster than a human can.
aw, quality over quantity, faster and more doesn't better? like I rather read the best three books than read lots of junks 😂
sorry if it's off topic
reply
272 sats \ 1 reply \ @kr OP 6 Jan
not sure it will stand out, but i think i’ve unlocked a new competitive advantage in being able to collect data much faster at much lower costs.
i think there could be some good crossover opportunities on SN, but those might be things like interactive Q&A sessions with book authors.
reply
I think the real cool would be how to collect the best sources of data much faster at much lower costs, haha.
i think there could be some good crossover opportunities on SN, but those might be things like interactive Q&A sessions with book authors
that would be nice: recommending really good books + discussions from real people, even with authors!
reply
Very nice look like interesting....
reply
Will try when you add Nostr sign in.
reply
why would i add any sign in at all? its just a list of books
reply
reply
that’s a sign up field for the bookmarked weekly newsletter
reply
408 sats \ 1 reply \ @shyfire 6 Jan
deleted by author
reply
  1. i never used mechanical turk, but Stakwork uses a combination of AI, humans, and automated workflows to solve different tasks
  2. nope, just a growing library of books recommended by interesting people
reply